Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    the word "only" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by degree adverbs, numbers, or limiters

    np_acts-logits-general · gemini-2.0-flash

    only followed by specific conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    only
    -0.71
     anche
    -0.68
    also
    -0.65
     hanya
    -0.64
    both
    -0.63
     både
    -0.63
     only
    -0.63
     jopa
    -0.63
     also
    -0.62
    λέον
    -0.61
    POSITIVE LOGITS
    fans
    0.91
     marginally
    0.86
     ever
    0.82
     للاسماء
    0.79
     onCreateView
    0.78
     rarely
    0.78
    Fans
    0.77
     partially
    0.73
     recently
    0.73
     thing
    0.72
    Act Density 0.211%

    No Known Activations